- Rating
- 2
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes FLRT, which uses Fork Exploration to disable future tools at real intermediate states and regenerate continuations, observing whether the model can answer correctly on its own to identify tool redundancy. This signal is used to construct SFT data and optimize tool use through RL based on answer correctness, call counts, and redundancy. Fork Exploration is not needed at deployment. Using GPT-OSS-20B and Python tools on AIME24, AIME25, and HMMT, mean accuracy increases from 76.30% to 79.77%, while the average number of calls decreases from 8.90 to 6.13.
Critical strengths
- A novel, interpretable state-level signal. Fork tests whether existing information suffices without further tools and generates successful continuations for training, providing more targeted supervision than call-count penalties alone.
- Higher accuracy with fewer calls. FLRT reaches 79.77% accuracy with about 31% fewer calls, versus 76.30% for Base and 59.62% without tools. Ablations offer preliminary support for the Fork signal beyond call counts.
Critical weaknesses
-
Fork reliability. Single-sample continuations and stopping at the first failed fork may make redundancy estimates and RL rankings noisy. Repeated sampling and exhaustive-scan comparisons are needed.
-
Attribution of training gains. Missing controls include Fork-ranked RL directly from Base and equal-data SFT without Fork. Incomplete checkpoint/configuration mappings and absent multi-seed results further limit the ablations. Matched-budget comparisons are needed.
-
Practical efficiency. Fewer calls do not establish end-to-end speedups. The reported RL overhead of about 12% excludes Fork data construction and SFT; full training costs, deployment token counts, and latency remain unreported.
-
Limited baseline coverage. Comparisons with EAPO, SMART, and full Probe&Prefill are missing; RTA is only a prompting baseline. These methods should be compared using the same model, tool environment, and comparable training budgets.
Questions for authors
- How stable are redundancy estimates and RL rankings under repeated Fork sampling or exhaustive scanning?
- How do direct Fork-ranked RL and SFT without Fork perform under matched budgets? Please clarify checkpoint/configuration mappings and report multi-seed results.
- What are the full training costs and deployment token counts, tool execution time, and end-to-end latency?